{
  "abstract": "Reliable population-graph evaluation requires separating cohort-conditioned discrimination from performance at an unseen site. We evaluate a recovered site-aware graph neural network in ABIDE-I (871 participants, 20 sites), distinguishing archived intervention results from newly recomputed controls. Archived cohort AUC was approximately 0.94, with high discrimination retained by site-only connectivity. A reconstructed ten-fold empirical site-prior classifier achieved pooled out-of-fold AUC 0.506 (95\\% site-resampling interval [0.418, 0.546]); simple site proportions therefore did not reproduce the high cohort result. In a budget-matched support-location experiment, the across-site mean AUC difference was +0.252 [0.184, 0.322] with directed edges but -0.003 [-0.020, 0.015] after symmetrisation, demonstrating implementation sensitivity rather than a stable support-location advantage. A supplementary leave-one-site-out analysis compared scoring-time population-edge access after the same source-site training procedure. Mean site-macro AUC was 0.577 with access and 0.580 without it; the paired difference was -0.0037 [-0.0179, 0.0111]. These observations do not establish equivalence or a complete mechanism. Explicit access contracts, compatible estimators and run-level provenance are necessary to interpret high transductive cohort performance.",
  "abstract_shown": true,
  "affiliations": [
    "National Center for Applied Mathematics, Chongqing Normal University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "K. Wan"
    },
    {
      "name": "Z. Chen"
    },
    {
      "name": "G. Liu"
    },
    {
      "name": "B. Yu"
    },
    {
      "affs": [
        0
      ],
      "name": "Q. Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "F. Zhang"
    },
    {
      "name": "N. Zhong"
    },
    {
      "name": "H. Kuai"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2mgmfg60tdmfz.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.15.751719",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751719v1.full",
  "id": "2mgmfg60tdmfz",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751719v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "neuroscience"
    ],
    [
      "openalex",
      "2805|Functional Brain Connectivity Studies"
    ]
  ],
  "openalex": "W7213930234",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751719v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2mgmfg60tdmfz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:33Z",
      "native_id": "10.64898/2026.09.15.751719",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.15.751719v5"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Tracing high transductive cohort AUC to same-site supervision in a site-aware population GNN for multisite fMRI",
  "title_text": "Tracing high transductive cohort AUC to same-site supervision in a site-aware population GNN for multisite fMRI",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:27Z",
  "url": "https://research.draconitic.com/paper/2mgmfg60tdmfz",
  "venue": "bioRxiv",
  "versions": []
}